> For the complete documentation index, see [llms.txt](https://lichangbin.gitbook.io/paper_notes/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://lichangbin.gitbook.io/paper_notes/nov/learning-to-adapt-to-evolving-domains.md).

# Learning to Adapt to Evolving Domains

## Presentation

slides could be found from the following link:

{% file src="/files/-MMHU8\_NdO66b3DsdnQR" %}
presentation slides by Changbin Li
{% endfile %}

## Questions

{% tabs %}
{% tab title="Q1: What is the role of Theorem 1?" %}
1\) approximate the loss function because no access to the label of target data
{% endtab %}
{% endtabs %}

{% tabs %}
{% tab title="Q2: What is the fundamental difference between EAML and MAML?" %}
MAML: learn a good initialization

EAML: learn meta-representation and meta-adapter
{% endtab %}
{% endtabs %}

{% tabs %}
{% tab title="Q3: What is the fundamental difference between the setting in the paper and continual learning?" %}

{% endtab %}
{% endtabs %}

{% tabs %}
{% tab title="Q4: What is A-distance? How could alpha affect the model?" %}

{% endtab %}
{% endtabs %}

{% tabs %}
{% tab title="Q5: Different assumptions about domain adaptation and domain generalization?" %}

{% endtab %}
{% endtabs %}

{% tabs %}
{% tab title="Q6: Catastrophic forgetting?" %}

{% endtab %}
{% endtabs %}

## Reference

* <https://papers.nips.cc/paper/2020/file/fd69dbe29f156a7ef876a40a94f65599-Paper.pdf>
* <https://github.com/Liuhong99/EAML>